AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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>
This commit is contained in:
Charis Poag
2024-01-24 20:43:47 -06:00
committed by Maisam Arif
parent 0b67c2ccc4
commit 34bd26c68e
7 changed files with 109 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/amd_smi/amdsmi.h
-6
View File
@@ -1385,12 +1385,6 @@ typedef struct {
// JPEG activity % per AID
uint16_t jpeg_activity[AMDSMI_MAX_NUM_JPEG];
// Memory Bandwidth Usage Accumulated (GB/sec)
uint64_t mem_bandwidth_acc;
// Memory Bandwidth Maximum (GB/sec)
uint32_t mem_max_bandwidth;
// PCIE NAK sent accumulated count
uint32_t pcie_nak_sent_count_acc;