Changes:
- Unique Id tries reading from KGD
-> falls back to use KFD if not found
Change-Id: I8fb8f38df5db7413805f4a20621ad12ed3fc89a3
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/rocm_smi_lib commit: 4276207ff8]
Changes:
- Unique Id tries reading from KGD
-> falls back to use KFD if not found
Change-Id: I8fb8f38df5db7413805f4a20621ad12ed3fc89a3
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
* Video file location change for rocDecode
* Formatting
* Changed rocJPEG images directory not found to a warning as well
* Minor name update
* Fix rocJPEG disable variable
[ROCm/rocprofiler-sdk commit: c4716afd1c]
* Video file location change for rocDecode
* Formatting
* Changed rocJPEG images directory not found to a warning as well
* Minor name update
* Fix rocJPEG disable variable
Add the new cmake option AMD_COMPUTE_WIN to build HIP on Windows
from the public github. AMD_COMPUTE_WIN should point to a special
repo with the PAL static libs
Do not use __ockl_activelane_u32() to calculate the index of the lane within the mask, as that would not work with divergent masks that have other bits on before the associated lane.
- Remove tooling initialization from rocprofiler_configure:
when rocprofiler configure is called from __hip_module_ctor
(which in turn is called as a global constructor when loading shared
libraries or before main in a hip program), initializing tooling
in it can cause problems because it is too early to do some of the tasks
that it involves (e.g. opening shared libraries, creating threads).
Instead, we rely on rocprofsys_main to initialize tooling later.
- Skip rocprofiler_configure if ROCPROFSYS_PRELOAD is not set since
preload is required for tooling (such as perfetto, which is used by
the rocprofiler callbacks) to be initialized.
- Revert RCCL initialization changes: These are no longer needed since rocprofsys_init_tooling_hidden will not
be called from rocprofiler_configure
- Force rocprofiler_configure in rocprofsys_init_tooling_hidden if it hasn't been
called through __hip_module_ctor global constructor
[ROCm/rocprofiler-systems commit: 0e535daa93]
- Remove tooling initialization from rocprofiler_configure:
when rocprofiler configure is called from __hip_module_ctor
(which in turn is called as a global constructor when loading shared
libraries or before main in a hip program), initializing tooling
in it can cause problems because it is too early to do some of the tasks
that it involves (e.g. opening shared libraries, creating threads).
Instead, we rely on rocprofsys_main to initialize tooling later.
- Skip rocprofiler_configure if ROCPROFSYS_PRELOAD is not set since
preload is required for tooling (such as perfetto, which is used by
the rocprofiler callbacks) to be initialized.
- Revert RCCL initialization changes: These are no longer needed since rocprofsys_init_tooling_hidden will not
be called from rocprofiler_configure
- Force rocprofiler_configure in rocprofsys_init_tooling_hidden if it hasn't been
called through __hip_module_ctor global constructor
* rocprofv3: LD_PRELOAD for signal and sigaction
- wrappers around `signal` and `sigaction` to prevent applications which install signal handlers to replace the rocprofv3 signal handlers
- minor tweaks to buffer sizes (use page_size instead of
KiB)
* [DO NOT COMMIT] extra logging
* Switch git submodule url for perfetto
- use GitHub URL as this is more accessible
* Update ring_buffer<Tp>
- account for alignment padding
* Update buffered_output
- track number of bytes stored
- add nullptr checks
* Update tmp_file_buffer
- track number of bytes
- read_tmp_file does not create tmp file if it does not already exist
* Update tmp_file
- add exists member function for checking whether temporary file already exists
- tweak remove() implementation
* Update config.hpp
- add option to enable/disable signal handlers
- add option for minimum_output_bytes
* Make signal, sigaction functions visible
* rocprofv3 tool updates
- chained signals
- override the signal handler(s) installed by the application
- improve cleanup of temporary files
- support minimum output bytes
* Add commandline support
* fixing test
* minor fix
* minor fix
* fix clang issue
* fix
* Adding docs
* review comments
* review changes
* review
* YUV pulldown additions to rocdecode
* More rocdecode changes
---------
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Jonathan R. Madsen <Jonathan.Madsen@amd.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>
[ROCm/rocprofiler-sdk commit: 87badfbd15]
* rocprofv3: LD_PRELOAD for signal and sigaction
- wrappers around `signal` and `sigaction` to prevent applications which install signal handlers to replace the rocprofv3 signal handlers
- minor tweaks to buffer sizes (use page_size instead of
KiB)
* [DO NOT COMMIT] extra logging
* Switch git submodule url for perfetto
- use GitHub URL as this is more accessible
* Update ring_buffer<Tp>
- account for alignment padding
* Update buffered_output
- track number of bytes stored
- add nullptr checks
* Update tmp_file_buffer
- track number of bytes
- read_tmp_file does not create tmp file if it does not already exist
* Update tmp_file
- add exists member function for checking whether temporary file already exists
- tweak remove() implementation
* Update config.hpp
- add option to enable/disable signal handlers
- add option for minimum_output_bytes
* Make signal, sigaction functions visible
* rocprofv3 tool updates
- chained signals
- override the signal handler(s) installed by the application
- improve cleanup of temporary files
- support minimum output bytes
* Add commandline support
* fixing test
* minor fix
* minor fix
* fix clang issue
* fix
* Adding docs
* review comments
* review changes
* review
* YUV pulldown additions to rocdecode
* More rocdecode changes
---------
Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Jonathan R. Madsen <Jonathan.Madsen@amd.com>
Co-authored-by: Benjamin Welton <bewelton@amd.com>
The compiler currently serializes the workgroup_processor_mode COMGR metadata boolean field as "0"/"1" instead of "false"/"true". Consider "1" a truthy value during parsing.
CPACK is converting /usr/bin/env python3 to /usr/libexec/platform-python in RHEL8.
This is resulting in dependency to platform-python
Undefining __brp_mangle_shebangs will prevent the same
[ROCm/rocprofiler-systems commit: 1c3616fcc2]
CPACK is converting /usr/bin/env python3 to /usr/libexec/platform-python in RHEL8.
This is resulting in dependency to platform-python
Undefining __brp_mangle_shebangs will prevent the same
xuchen-amd
Poag, Charis
Saleel Kudchadker
cfallows-amd
Trowbridge, Ian
GunaShekar, Ajay
Hila, Nino
Andryeyev, German
Bhardwaj, Gopesh
dependabot[bot]
Hernandez, Gerardo
Sohaib Nadeem
Vaddireddy, Sushma
Amber Lin
Elwazir, Ammar
Godavarthy Surya, Anusha
David Galiffi
Brzak, Branislav
Nagaraj, Sriraksha
Baraldi, Giovanni
Yiannis Papadopoulos
Stojiljkovic, Vladana
Ramirez, Lucas
raramakr
Sajina PK