* SWDEV-518831 - fix streams' sync issue in mthreads
1. Fix sync issue of null stream and non-null streams in
multithreads.
2. Remove assert(GetSubmissionBatch() == nullptr) as it
is invalid in multithreads.
3. Update getActiveQueues() to deal with the state of
being terminated.
[ROCm/clr commit: 27aad09bd4]
* SWDEV-518831 - fix streams' sync issue in mthreads
1. Fix sync issue of null stream and non-null streams in
multithreads.
2. Remove assert(GetSubmissionBatch() == nullptr) as it
is invalid in multithreads.
3. Update getActiveQueues() to deal with the state of
being terminated.
Fix monitor hang in cts integer_ops.
Improve notify().
Won't affect notifyAll() and Hip in direct
dispatch mode.
Change-Id: I95a458358e1cab9c76aefde117db09cdbd1fd3af
[ROCm/clr commit: 78f92901d8]
Fix monitor hang in cts integer_ops.
Improve notify().
Won't affect notifyAll() and Hip in direct
dispatch mode.
Change-Id: I95a458358e1cab9c76aefde117db09cdbd1fd3af
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>
- Add a new AMD extension API to return preferred SDMA engine mask.
This can use used in conjunction with copy_on_engine API to get
optimal bandwidth.
[ROCm/ROCR-Runtime commit: 57c0c643ce]
* 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
[ROCm/clr commit: a3effa16f1]
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.
[ROCm/clr commit: 1a8d766836]
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
Sang, Tao
Xie, Jiabao(Jimbo)
Hila, Nino
Choudhary, Rahul
xuchen-amd
Poag, Charis
Saleel Kudchadker
cfallows-amd
Trowbridge, Ian
GunaShekar, Ajay
Andryeyev, German
Bhardwaj, Gopesh
dependabot[bot]
Hernandez, Gerardo
Sohaib Nadeem
Vaddireddy, Sushma