Changes: - Fixed Device Name (market name)
- Added new API rsmi_dev_market_name_get()
- Updated tests
- Updated amdgpu_drm.h to match latest mainline kernel
- Fixed subsystem ID to only show hex value (not subsystem name)
- rocm_smi_lib now has a recommended requirement for libdrm
Change-Id: Ic438529e16c8c3dbbdd620da664918148c40c997
1) When `clang` is used as system compiler, libraries were built without respecting LDFLAGS. For example, this affected LTO flags, if any (and it only affected clang, not gcc).
2) Linker flags are registered as CXX flags, which produces warnings during compilation:
```
clang++: warning: -Wl,-z,noexecstack: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-znoexecheap: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,relro: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,now: 'linker' input unused [-Wunused-command-line-argument]
```
3) Clang does not support `-Wtrampolines` flag:
```
warning: unknown warning option '-Wtrampolines' [-Wunknown-warning-option]
```
4) No linkers support `noexecheap` anymore. `noexecheap` linker flag was a part of PaX patches to GNU ld, (which were dropped in 2017)[https://www.gentoo.org/support/news-items/2017-08-19-hardened-sources-removal.html]. Now ld/ld.lld/ld.gold don't support it and protection of heap is managed by NX bit. Therefore every compiler produces this warning:
```
ld.lld: warning: unknown -z value: noexecheap
```
Closes#210.
Co-authored-by: Sv. Lockal <lockalsash@gmail.com>
In centos-7, python2 is used for cpack bytecompile. Using f strings in code will result in syntax error.
Setting _python_bytecompile_errors_terminate_build to 0 will ignore the errors
Change-Id: I43ecc99ae16627f4f5f91d0cca0398f6a003fa3c
CPACK is converting /usr/bin/env python3 to /usr/libexec/platform-python in RHEL8.
Undefining __brp_mangle_shebangs will prevent the same
Change-Id: Id285e2cea1de583853cec17eccf0a3a794cca643
The provides tag is required when the package provides a virtual package.
Package name along with version will be provided by default and the provides tag is not required for this.
Using the tag for providing the name, but without version was resulting in package upgrade issues.
Change-Id: I74506d8c3bbd75d028bcdc03525c29541dce2b4c
Code changes related to the following:
* Check smallest copy size for multi-valued metrics
* Unit tests: gpu_metric_read
* ROCMSMI examples
Build changes related to the following:
* CMakeLists.txt
Change-Id: Ieb2363020fa21c93fbacd0edcc1d394eed183051
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
- std=c++.. is not required because CMAKE_CXX_STANDARD is set
- nullptr check breaks the test because we rely on nullptr as an api for
checking feature availability.
- enum number setting is unnecessary
Change-Id: I393e6dd3f292b7fa4198302f140c0443ba5e50f5
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
* Updates:
- [API/CLI] rsmi_dev_*_partition_set &
rsmi_dev_*_partition_reset - exposed RSMI_STATUS_BUSY for
EBUSY writes + cleaned up accidental map insertions
(maplookup[] can insert values that are not in the map,
map.at(key) fixes this potential issue)
- [API] rsmi_dev_gpu_metrics_info_get() - returns
RSMI_STATUS_NOT_SUPPORTED for unsupported metric tables
outside of 1v1/1v2/1v3
- [API] writeDevInfoStr() - exposes RSMI_STATUS_BUSY for
EBUSY write errors; kept backward compatibility
for other writes which do not care about these states
- [API] rsmi_dev_od_volt_info_get()
& rsmi_dev_od_volt_curve_regions_get() have better logging
+ Expose more details on why they are erroring
- [Utils/logs/example] Expose AMD GPU gfx target version to aid in
system troubleshooting
- [Utils] Added test methods that look at od volt
freq & regions into here - for easier access across
several tests
- [Utils] Updated getRSMIStatusString(new argument - fullstatus;
default to true for backwards compatibility)
-> true shows shortened RSMI STATUS response
- [Utils] Added splitString to cut out noisy return responses
(used in getRSMIStatusString(), when fullstatus = true)
- [Utils] Added getFileCreationDate() to expose build date
of the library - helpful for local builds or experimental builds
- [Utils] Macro cleanup
- [Example] Added a few gpu_metric checks - helpful for upcoming
updates
- [Device] SYSFS/DebugFS - now have better r/w displayed in logs
- [LOGS] Expose library build date - see above for details
- [Tests] Add more warnings/errors to test builds
- [Tests] Moved up Partition tests for ordered test runs - helped
identify issues with GPU BUSY writes
- [Tests] compute_partition_read_write - handles RSMI_STATUS_BUSY
with waits for busy status found & cleaned up how we checked
for partition changes - with RSMI responses exposed more clearly
- [Tests] perf_determinism - multi gpu now properly runs through
with full resets as needed
- [Tests] volt_freq_curv_read - better error handling with more
verbose output
Change-Id: Ie94c6abb6a9aab95c345996d3ad3843cf6734977
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
When built with LTO enabled, the linking of liboam.so chokes on the
following error, which is somewhat similar to the Debian bug #1030876
affecting PA-RISC, although the symptoms subtly differs in that it
suggests to build using -fPIC:
/usr/bin/ld: /tmp/cc0wF8Kx.ltrans0.ltrans.o: relocation R_X86_64_PC32 against symbol `_ZTVSt9exception@@GLIBCXX_3.4' can not be used when making a shared object; recompile with -fPIC
The -fPIC argument is passed appropriately down to the build command,
however it looks to be erased by the late introduction of -fPIE flag
by upstream build system. Erasing this flag allows the build to go
through, both with LTO and on PA-RISC.
Bug: https://github.com/RadeonOpenCompute/rocm_smi_lib/issues/111
Bug-Debian: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1015653
Change-Id: I8b35fd4b62cfa1a9ddb145362464df5dd276e2f5
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Adds support for 'gpu_metrics_v1_4' and new counters
Code changes related to the following:
* rsmi gpu_metrics APIs
* rsmi gpu_metrics Logs
* The new gpu_metrics are now part of the Device
Build changes related to the following: None
Change-Id: Ie748e977cd0a01c6a2fb82260014c0699605dbb3
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
Also change the TARGET from amd_smi_libraries to rocm_smi_libraries
This helps reduce confusion between rocm-smi and amd-smi
Change-Id: Ie54cedd831ba24bd9afc341ad15b7e8e20732059
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Code changes related to the following:
* All reinforcement work moved to their own files
* Self contained changes only to support them
* New files added to CMakeLists.txt
Change-Id: I761e91f54392824df9145eaed8b9805986861285
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
There seems to be a scope issue with the existing variables, but just
putting in the pkg version string seems sufficient.
Change-Id: I4ccef872ff848a70cb2abc07bf605c5f29a608e8
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
When building from github, these tags don't exist, so the defaults
should try to match the internal tags
Change-Id: Id570341f27e21916b1a7f3605ee2b5b9716cad9b
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
This looks like a typo, as the following variables are not defined:
- AMD_SMI_LIBS_TARGET_VERSION_MAJOR
- AMD_SMI_LIBS_TARGET_VERSION_MINOR
- AMD_SMI_LIBS_TARGET_VERSION_PATCH
Change-Id: I43449e7bd2a2de643d33e79fad063a7859679c8d
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Updates:
* [rocm-smi] Provide a thread-safe logging feature
* [rocm-smi] Adding logrotation into install/upgrade/remove
scripts
* [rocm-smi] Updated cmake lists to include rocm_smi_logger
* [rocm-smi] Updated DEB/RPM install/remove logging file &
folder with all users having r/w privledges for
/var/log/rocm_smi_lib/ROCm-SMI-lib.log
* [rocm-smi] Added ability to do a glob search for multiple files
(globFileExists), assists doing file searches with * strings
* [rocm-smi] Added ability to log system details when RSMI_LOGGING
is turned on (getSystemDetails())
* [rocm-smi] Added logging to provide which ROCm API is being called
when RSMI_LOGGING is on
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added logging to provide SYSFS path and read value,
when RSMI_LOGGING is on. Provides error reponse on failure.
* [rocm-smi] Added environment variable RSMI_LOGGING to control
when logging is enabled or disabled. By default, by not
setting this env. variable, logging is turned off. When
setting RSMI_LOGGING=<any value>, logging is enabled
which is placed in /var/log/rocm_smi_lib/ROCm-SMI-lib.log file.
Setting RSMI_LOGGING is allowed in both debug and release builds.
* [rocm-smi] Removed an initialize procedure which keeps
debug_inf_loop. Seems this feature is not being used.
Change-Id: I79b48387609c6233c6f05b04fb8bba66b68c2399
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Using backward compatibility paths will provide an #error message. Compile time option added to enable/disable the #error message.
Disabling the same will provide a #warning message
Change-Id: Ib49633501aa6eb6d97158b1ecfc47de6f18fba85
I6520b51aac34060b5b90f94a016cec1827a4973f happens after uninstall, which
leaves a dangling directory under /opt/rocm/libexec/rocm_smi.
Removing __pycache__ before uninstall fixes the issue.
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
Change-Id: I695bd085d4a43b678b563b4c35f6d2e8ddfa7d7c
Any default value if required should be controlled from outside.
For ROCM, build script is setting the value to "lib"
Change-Id: I12a2951307fe64e46a4e608476bfceb678bdc97d
Use GNUInstallDirs variables to determine the location of LIBDIR, BINDIR, INCLUDEDIR, DOCDIR
Note that CMAKE_INSTALL_LIBDIR is overriden, since the default for RHEL
is lib64, but ROCm packaging wants it to be lib always. Distros or users
can easily override this.
Change-Id: I616152ccd2bc1f5a60bffa940312b38ca6e88c04
Wrapper header files
Soft link to libraries and binaries
rocm_smi.py and rsmiBindings.py installed in libexec/rocm_smi
Binaries, libraries and header files installed as per File Reorg folder structure
Change-Id: I3166ab67f89c2ae4aafbc87bb00c9a5233221ade
Galantsev, Dmitrii
Charis Poag
Ranjith Ramakrishnan
Maisam Arif
Daniel Martinez
Oliveira, Daniel
Étienne Mollier
Jeremy Newton
AravindanC
Freddy Paul
Bill(Shuzhou) Liu
Icarus Sparry