CMakelist updated to latest esmi tag esmi_pkg_ver-4.2, which
has fixes for esmi warnings during amdsmi build,
amdsmi_get_cpu_current_xgmi_bw updated as per change in
corresponding esmi library API
Signed-off-by: Deepak Mewar <deepak.mewar@amd.com>
CMakelist updated to latest esmi tag esmi_pkg_ver-4.2, which
has fixes for esmi warnings during amdsmi build,
amdsmi_get_cpu_current_xgmi_bw updated as per change in
corresponding esmi library API
Signed-off-by: Deepak Mewar <deepak.mewar@amd.com>
[ROCm/amdsmi commit: 49aa2af045]
Also add flag: HIP_FORCE_SPIRV_CODEOBJECT to allow override to force use
SPIRV.
* use cache for already compiled code objects
* address review comments and use the two spirv isa names
[ROCm/clr commit: 07e57a1f0d]
Also add flag: HIP_FORCE_SPIRV_CODEOBJECT to allow override to force use
SPIRV.
* use cache for already compiled code objects
* address review comments and use the two spirv isa names
* Changes:
- Updates to DRM renderD* / card* pathing for partition devices
- Now use KFD to discover AMD devices and populate accordingly
Device MUST have an accessible KFD node (via cgroups)
- Updated several ROCm SMI CLI outputs to handle SYSFS files
which are not accessible on partition nodes
- Added a new method to help get card/drm info
(rsmi_dev_device_identifiers_get) from ROCm SMI
Change-Id: If844f27ffc595942272abe9c8167ed90a0b0e225
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: a0df877fdf]
* Changes:
- Updates to DRM renderD* / card* pathing for partition devices
- Now use KFD to discover AMD devices and populate accordingly
Device MUST have an accessible KFD node (via cgroups)
- Updated several ROCm SMI CLI outputs to handle SYSFS files
which are not accessible on partition nodes
- Added a new method to help get card/drm info
(rsmi_dev_device_identifiers_get) from ROCm SMI
Change-Id: If844f27ffc595942272abe9c8167ed90a0b0e225
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
rocm-smi is not working in mGPU, Blocking DLM tests
Updates include:
- Creating check_runtime_status function to check for device status of active.
- Added warning to users that No AMD GPUs are available, check power status/control.
- Added check for empty string coming from HWMON, if emtpy returns unexpected data.
---------
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
[ROCm/rocm_smi_lib commit: 2630bf0a8c]
rocm-smi is not working in mGPU, Blocking DLM tests
Updates include:
- Creating check_runtime_status function to check for device status of active.
- Added warning to users that No AMD GPUs are available, check power status/control.
- Added check for empty string coming from HWMON, if emtpy returns unexpected data.
---------
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
* add code for bootstrapping
the bootstrapping code has been extracted from the MSCCLPP library,
which in parts is based on the code from NVIDIA. The code has been
modified to match the specific requirements of the rocSHMEM library.
* add code to use the new uniqueId bootstrapping
* adjust init_attr example
extend the rocshmem_init_attr example to use two disjoint groups
of processe, in order to trigger the new code path.
* add env variable for bootstrap timeout
* Update examples/rocshmem_init_attr_test.cc
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
* Update src/rocshmem.cpp
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
---------
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
[ROCm/rocshmem commit: b5830a623b]
* add code for bootstrapping
the bootstrapping code has been extracted from the MSCCLPP library,
which in parts is based on the code from NVIDIA. The code has been
modified to match the specific requirements of the rocSHMEM library.
* add code to use the new uniqueId bootstrapping
* adjust init_attr example
extend the rocshmem_init_attr example to use two disjoint groups
of processe, in order to trigger the new code path.
* add env variable for bootstrap timeout
* Update examples/rocshmem_init_attr_test.cc
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
* Update src/rocshmem.cpp
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
---------
Co-authored-by: Aurelien Bouteiller <Aurelien.bouteiller@gmail.com>
This is required for GPU busy percent in RDC
Change-Id: Idf2ab72993ecc8227958e6eb47f36fc68c93759f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
This is required for GPU busy percent in RDC
Change-Id: Idf2ab72993ecc8227958e6eb47f36fc68c93759f
Signed-off-by: Galantsev, Dmitrii <dmitrii.galantsev@amd.com>
[ROCm/amdsmi commit: 955ceac78a]
* Set version for RPM_PACKAGE_OBSOLETES
* Not setting a version of omnitrace which rocprofiler-systems obsoletes will result in a warning
* Patch RPATH in libunwind files
* Update Timemory pointer
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
---------
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
[ROCm/rocprofiler-systems commit: 75916f8876]
* Set version for RPM_PACKAGE_OBSOLETES
* Not setting a version of omnitrace which rocprofiler-systems obsoletes will result in a warning
* Patch RPATH in libunwind files
* Update Timemory pointer
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
---------
Signed-off-by: David Galiffi <David.Galiffi@amd.com>
* Update backend to use provided MPI communicator during library initialization, default to `MPI_COMM_WORLD`
* Update `rocshmem_my_pe` and `rocshmem_n_pes` host APIs
- Return values from backend if initialized; otherwise, fallback to MPI_Singleton.
[ROCm/rocshmem commit: 05755847f5]
* Update backend to use provided MPI communicator during library initialization, default to `MPI_COMM_WORLD`
* Update `rocshmem_my_pe` and `rocshmem_n_pes` host APIs
- Return values from backend if initialized; otherwise, fallback to MPI_Singleton.
HSA_TOOLS_LIB is not respected for some pytorch APPs
Instead of depending on HSA_TOOLS_LIB, move to depending on LD_PRELOAD for loading the rocprofiler library.
HSA_TOOLS_LIB is not respected for some pytorch APPs
Instead of depending on HSA_TOOLS_LIB, move to depending on LD_PRELOAD for loading the rocprofiler library.
[ROCm/rocprofiler commit: f23fe43c29]
* Changes:
- Updates to DRM renderD* / card* pathing for partition
- Now use KFD to discover AMD devices and populate accordingly
Device MUST have an accessible KFD node (via cgroups)
- Updated serveral AMD SMI CLI outputs to handle SYSFS files
which are not accessible on partition nodes
- Tests are updated to handle not supported features
- Added new method to help get card/drm info
(rsmi_dev_device_identifiers_get) from ROCm SMI
- Renamed device->get_card_id() & device->get_drm_render_minor()
These can now be used on internal AMD SMI calls.
- Removed warnings shown in build
Change-Id: Ice882fd9b97fb625a5bd4ef327f3ceaf247dc570
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
* Changes:
- Updates to DRM renderD* / card* pathing for partition
- Now use KFD to discover AMD devices and populate accordingly
Device MUST have an accessible KFD node (via cgroups)
- Updated serveral AMD SMI CLI outputs to handle SYSFS files
which are not accessible on partition nodes
- Tests are updated to handle not supported features
- Added new method to help get card/drm info
(rsmi_dev_device_identifiers_get) from ROCm SMI
- Renamed device->get_card_id() & device->get_drm_render_minor()
These can now be used on internal AMD SMI calls.
- Removed warnings shown in build
Change-Id: Ice882fd9b97fb625a5bd4ef327f3ceaf247dc570
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: 4782528770]
Maisam Arif
Mewar, Deepak
Aryan Salmanpour
Chaudhary, Jatin Jaikishan
Charis Poag
jeffqjiangNew
Trowbridge, Ian
Castillo, Juan
Edgar Gabriel
Galantsev, Dmitrii
David Galiffi
AbandiGa
Avinash Kethineedi
Elwazir, Ammar
Kanangot Balakrishnan, Bindhiya
Giuseppe Congiu
Justin Williams
ywang103-amd