SWDEV-445396 - Aligned Static Command with Host

Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I4182b9104e173f54830fc44819a61d74d31d65d7
This commit is contained in:
Maisam Arif
2024-02-21 21:46:32 -06:00
committed by Maisam Arif
parent db33cda0c1
commit a719ae9707
5 changed files with 133 additions and 178 deletions
+84 -144
View File
@@ -637,8 +637,8 @@ BOARD:
MODEL_NUMBER: N/A
PRODUCT_SERIAL: N/A
FRU_ID: N/A
MANUFACTURER_NAME: N/A
PRODUCT_NAME: N/A
MANUFACTURER_NAME: N/A
LIMIT:
MAX_POWER: 550 W
CURRENT_POWER: 0 W
@@ -649,13 +649,13 @@ LIMIT:
SHUTDOWN_HOTSPOT_TEMPERATURE: 110 °C
SHUTDOWN_VRAM_TEMPERATURE: 105 °C
DRIVER:
DRIVER_NAME: amdgpu
DRIVER_VERSION: 6.5.2
NAME: amdgpu
VERSION: 6.5.2
VRAM:
VRAM_TYPE: HBM
VRAM_VENDOR: HYNIX
VRAM_SIZE_MB: 96432 MB
CACHE:
TYPE: HBM
VENDOR: N/A
SIZE: 96432 MB
CACHE_INFO:
CACHE_0:
CACHE_PROPERTIES: DATA_CACHE, SIMD_CACHE
CACHE_SIZE: 32 KB
@@ -688,34 +688,20 @@ RAS:
DOUBLE_BIT_SCHEMA: DISABLED
POISON_SCHEMA: ENABLED
ECC_BLOCK_STATE:
BLOCK: UMC
STATUS: DISABLED
BLOCK: SDMA
STATUS: ENABLED
BLOCK: GFX
STATUS: ENABLED
BLOCK: MMHUB
STATUS: ENABLED
BLOCK: ATHUB
STATUS: DISABLED
BLOCK: PCIE_BIF
STATUS: DISABLED
BLOCK: HDP
STATUS: DISABLED
BLOCK: XGMI_WAFL
STATUS: DISABLED
BLOCK: DF
STATUS: DISABLED
BLOCK: SMN
STATUS: DISABLED
BLOCK: SEM
STATUS: DISABLED
BLOCK: MP0
STATUS: DISABLED
BLOCK: MP1
STATUS: DISABLED
BLOCK: FUSE
STATUS: DISABLED
UMC: DISABLED
SDMA: ENABLED
GFX: ENABLED
MMHUB: ENABLED
ATHUB: DISABLED
PCIE_BIF: DISABLED
HDP: DISABLED
XGMI_WAFL: DISABLED
DF: DISABLED
SMN: DISABLED
SEM: DISABLED
MP0: DISABLED
MP1: DISABLED
FUSE: DISABLED
PARTITION:
COMPUTE_PARTITION: SPX
MEMORY_PARTITION: NPS1
@@ -748,8 +734,8 @@ BOARD:
MODEL_NUMBER: N/A
PRODUCT_SERIAL: N/A
FRU_ID: N/A
MANUFACTURER_NAME: N/A
PRODUCT_NAME: N/A
MANUFACTURER_NAME: N/A
LIMIT:
MAX_POWER: 550 W
CURRENT_POWER: 0 W
@@ -760,14 +746,13 @@ LIMIT:
SHUTDOWN_HOTSPOT_TEMPERATURE: 110 °C
SHUTDOWN_VRAM_TEMPERATURE: 105 °C
DRIVER:
DRIVER_NAME: amdgpu
DRIVER_VERSION: 6.5.2
NAME: amdgpu
VERSION: 6.5.2
VRAM:
VRAM_TYPE: HBM
VRAM_VENDOR: HYNIX
VRAM_SIZE_MB: 96432 MB
CACHE:
CACHE:
TYPE: HBM
VENDOR: N/A
SIZE: 96432 MB
CACHE_INFO:
CACHE_0:
CACHE_PROPERTIES: DATA_CACHE, SIMD_CACHE
CACHE_SIZE: 32 KB
@@ -799,34 +784,20 @@ RAS:
DOUBLE_BIT_SCHEMA: DISABLED
POISON_SCHEMA: ENABLED
ECC_BLOCK_STATE:
BLOCK: UMC
STATUS: DISABLED
BLOCK: SDMA
STATUS: ENABLED
BLOCK: GFX
STATUS: ENABLED
BLOCK: MMHUB
STATUS: ENABLED
BLOCK: ATHUB
STATUS: DISABLED
BLOCK: PCIE_BIF
STATUS: DISABLED
BLOCK: HDP
STATUS: DISABLED
BLOCK: XGMI_WAFL
STATUS: DISABLED
BLOCK: DF
STATUS: DISABLED
BLOCK: SMN
STATUS: DISABLED
BLOCK: SEM
STATUS: DISABLED
BLOCK: MP0
STATUS: DISABLED
BLOCK: MP1
STATUS: DISABLED
BLOCK: FUSE
STATUS: DISABLED
UMC: DISABLED
SDMA: ENABLED
GFX: ENABLED
MMHUB: ENABLED
ATHUB: DISABLED
PCIE_BIF: DISABLED
HDP: DISABLED
XGMI_WAFL: DISABLED
DF: DISABLED
SMN: DISABLED
SEM: DISABLED
MP0: DISABLED
MP1: DISABLED
FUSE: DISABLED
PARTITION:
COMPUTE_PARTITION: SPX
MEMORY_PARTITION: NPS1
@@ -859,8 +830,8 @@ BOARD:
MODEL_NUMBER: N/A
PRODUCT_SERIAL: N/A
FRU_ID: N/A
MANUFACTURER_NAME: N/A
PRODUCT_NAME: N/A
MANUFACTURER_NAME: N/A
LIMIT:
MAX_POWER: 550 W
CURRENT_POWER: 0 W
@@ -871,14 +842,13 @@ LIMIT:
SHUTDOWN_HOTSPOT_TEMPERATURE: 110 °C
SHUTDOWN_VRAM_TEMPERATURE: 105 °C
DRIVER:
DRIVER_NAME: amdgpu
DRIVER_VERSION: 6.5.2
NAME: amdgpu
VERSION: 6.5.2
VRAM:
VRAM_TYPE: HBM
VRAM_VENDOR: HYNIX
VRAM_SIZE_MB: 96432 MB
CACHE:
CACHE:
TYPE: HBM
VENDOR: N/A
SIZE: 96432 MB
CACHE_INFO:
CACHE_0:
CACHE_PROPERTIES: DATA_CACHE, SIMD_CACHE
CACHE_SIZE: 32 KB
@@ -910,34 +880,20 @@ RAS:
DOUBLE_BIT_SCHEMA: DISABLED
POISON_SCHEMA: ENABLED
ECC_BLOCK_STATE:
BLOCK: UMC
STATUS: DISABLED
BLOCK: SDMA
STATUS: ENABLED
BLOCK: GFX
STATUS: ENABLED
BLOCK: MMHUB
STATUS: ENABLED
BLOCK: ATHUB
STATUS: DISABLED
BLOCK: PCIE_BIF
STATUS: DISABLED
BLOCK: HDP
STATUS: DISABLED
BLOCK: XGMI_WAFL
STATUS: DISABLED
BLOCK: DF
STATUS: DISABLED
BLOCK: SMN
STATUS: DISABLED
BLOCK: SEM
STATUS: DISABLED
BLOCK: MP0
STATUS: DISABLED
BLOCK: MP1
STATUS: DISABLED
BLOCK: FUSE
STATUS: DISABLED
UMC: DISABLED
SDMA: ENABLED
GFX: ENABLED
MMHUB: ENABLED
ATHUB: DISABLED
PCIE_BIF: DISABLED
HDP: DISABLED
XGMI_WAFL: DISABLED
DF: DISABLED
SMN: DISABLED
SEM: DISABLED
MP0: DISABLED
MP1: DISABLED
FUSE: DISABLED
PARTITION:
COMPUTE_PARTITION: SPX
MEMORY_PARTITION: NPS1
@@ -970,8 +926,8 @@ BOARD:
MODEL_NUMBER: N/A
PRODUCT_SERIAL: N/A
FRU_ID: N/A
MANUFACTURER_NAME: N/A
PRODUCT_NAME: N/A
MANUFACTURER_NAME: N/A
LIMIT:
MAX_POWER: 550 W
CURRENT_POWER: 0 W
@@ -982,15 +938,13 @@ LIMIT:
SHUTDOWN_HOTSPOT_TEMPERATURE: 110 °C
SHUTDOWN_VRAM_TEMPERATURE: 105 °C
DRIVER:
DRIVER_NAME: amdgpu
DRIVER_VERSION: 6.5.2
NAME: amdgpu
VERSION: 6.5.2
VRAM:
VRAM_TYPE: HBM
VRAM_VENDOR: HYNIX
VRAM_SIZE_MB: 96432 MB
CACHE:
CACHE_0:
CACHE:
TYPE: HBM
VENDOR: N/A
SIZE: 96432 MB
CACHE_INFO:
CACHE_0:
CACHE_PROPERTIES: INST_CACHE, SIMD_CACHE
CACHE_SIZE: 32 KB
@@ -1022,34 +976,20 @@ RAS:
DOUBLE_BIT_SCHEMA: DISABLED
POISON_SCHEMA: ENABLED
ECC_BLOCK_STATE:
BLOCK: UMC
STATUS: DISABLED
BLOCK: SDMA
STATUS: ENABLED
BLOCK: GFX
STATUS: ENABLED
BLOCK: MMHUB
STATUS: ENABLED
BLOCK: ATHUB
STATUS: DISABLED
BLOCK: PCIE_BIF
STATUS: DISABLED
BLOCK: HDP
STATUS: DISABLED
BLOCK: XGMI_WAFL
STATUS: DISABLED
BLOCK: DF
STATUS: DISABLED
BLOCK: SMN
STATUS: DISABLED
BLOCK: SEM
STATUS: DISABLED
BLOCK: MP0
STATUS: DISABLED
BLOCK: MP1
STATUS: DISABLED
BLOCK: FUSE
STATUS: DISABLED
UMC: DISABLED
SDMA: ENABLED
GFX: ENABLED
MMHUB: ENABLED
ATHUB: DISABLED
PCIE_BIF: DISABLED
HDP: DISABLED
XGMI_WAFL: DISABLED
DF: DISABLED
SMN: DISABLED
SEM: DISABLED
MP0: DISABLED
MP1: DISABLED
FUSE: DISABLED
PARTITION:
COMPUTE_PARTITION: SPX
MEMORY_PARTITION: NPS1
+28 -12
View File
@@ -399,8 +399,8 @@ class AMDSMICommands():
static_dict['board'] = {"model_number": "N/A",
"product_serial": "N/A",
"fru_id": "N/A",
"manufacturer_name": "N/A",
"product_name": "N/A"}
"product_name": "N/A",
"manufacturer_name": "N/A"}
try:
board_info = amdsmi_interface.amdsmi_get_gpu_board_info(args.gpu)
for key, value in board_info.items():
@@ -524,17 +524,21 @@ class AMDSMICommands():
limit_info['shutdown_vram_temperature'] = shutdown_temp_vram_limit
static_dict['limit'] = limit_info
if args.driver:
driver_info = {"driver_name" : "N/A",
"driver_version" : "N/A"
}
driver_info_dict = {"name" : "N/A",
"version" : "N/A"}
try:
driver_info = amdsmi_interface.amdsmi_get_gpu_driver_info(args.gpu)
driver_info_dict["name"] = driver_info["driver_name"]
driver_info_dict["version"] = driver_info["driver_version"]
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get driver info for gpu %s | %s", gpu_id, e.get_error_info())
static_dict['driver'] = driver_info
static_dict['driver'] = driver_info_dict
if args.vram:
vram_info_dict = {"type" : "N/A",
"vendor" : "N/A",
"size" : "N/A"}
try:
vram_info = amdsmi_interface.amdsmi_get_gpu_vram_info(args.gpu)
@@ -556,16 +560,24 @@ class AMDSMICommands():
# Remove amdsmi enum prefix
vram_vendor = vram_vendor.replace('AMDSMI_VRAM_VENDOR__', '')
vram_info['vram_type'] = vram_type
vram_info['vram_vendor'] = vram_vendor
# Assign cleaned values to vram_info_dict
vram_info_dict['type'] = vram_type
vram_info_dict['vendor'] = vram_vendor
# Populate vram size with unit
vram_info_dict['size'] = vram_info['vram_size_mb']
vram_size_unit = "MB"
if self.logger.is_human_readable_format():
vram_info['vram_size_mb'] = f"{vram_info['vram_size_mb']} MB"
vram_info_dict['size'] = f"{vram_info['vram_size_mb']} {vram_size_unit}"
if self.logger.is_json_format():
vram_info_dict['size'] = {"value" : vram_info['vram_size_mb'],
"unit" : vram_size_unit}
except amdsmi_exception.AmdSmiLibraryException as e:
vram_info = "N/A"
logging.debug("Failed to get vram info for gpu %s | %s", gpu_id, e.get_error_info())
static_dict['vram'] = vram_info
static_dict['vram'] = vram_info_dict
if args.cache:
try:
cache_info_list = amdsmi_interface.amdsmi_get_gpu_cache_info(args.gpu)['cache']
@@ -628,7 +640,11 @@ class AMDSMICommands():
logging.debug("Failed to get ras info for gpu %s | %s", gpu_id, e.get_error_info())
try:
ras_dict["ecc_block_state"] = amdsmi_interface.amdsmi_get_gpu_ras_block_features_enabled(args.gpu)
ras_states = amdsmi_interface.amdsmi_get_gpu_ras_block_features_enabled(args.gpu)
ecc_block_state_dict = {}
for state in ras_states:
ecc_block_state_dict[state["block"]] = state["status"]
ras_dict["ecc_block_state"] = ecc_block_state_dict
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get ras block features for gpu %s | %s", gpu_id, e.get_error_info())