rocm_smi_lib: Fix Refactoring gpu_metrics code

Uses new support for 'gpu_metrics_v1_4'

Code changes related to the following:
  * rsmi gpu_metrics APIs
  * rsmi gpu_metrics Logs
  * new data structure fields added in 1.4
  * added APIs for all other existing metrics before 1.4
  * added support to older metrics; 1.1, and 1.2
  * public APIs renamed to start with prefix 'rsmi_dev_metrics_'
  * Unit tests updated
  * Examples updated

Build changes related to the following: None

Change-Id: Ibdaf031be9d916020b4049544dbd725858c7711d
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
This commit is contained in:
Oliveira, Daniel
2023-10-24 21:12:05 -05:00
parent e5627d2bf1
commit 2c8ba4cae9
11 changed files with 5624 additions and 933 deletions
+958 -64
View File
File diff suppressed because it is too large Load Diff
+9 -2
View File
@@ -530,7 +530,7 @@ static const std::map<const char *, dev_depends_t> kDevFuncDependsMap = {
Device::Device(std::string p, RocmSMI_env_vars const *e) :
monitor_(nullptr), path_(p), env_(e), evt_notif_anon_fd_(-1),
gpu_metrics_ver_{0, 0, 0} {
m_gpu_metrics_header{0, 0, 0} {
#ifndef DEBUG
env_ = nullptr;
#endif
@@ -875,7 +875,14 @@ int Device::readDevInfoBinary(DevInfoTypes type, std::size_t b_size,
if ((num*b_size) != b_size) {
ss << "Could not read DevInfoBinary for DevInfoType ("
<< RocmSMI::devInfoTypesStrings.at(type) << ") - SYSFS ("
<< sysfs_path << "), binary size error, "
<< sysfs_path << "), binary size error; "
<< "[buff: "
<< p_binary_data
<< " size: "
<< b_size
<< " read: "
<< num
<< "]"
<< ", returning ENOENT (" << std::strerror(ENOENT) << ")";
LOG_ERROR(ss);
return ENOENT;
+1720 -700
View File
File diff suppressed because it is too large Load Diff