Adds a bool to the GPU agent and a public member method to
check if the GPU supports large BAR. This is needed so we can
check if large BAR is supported when a user tries to allocate
an AQL queue in device memory on a given GPU agent.
Also adds an exception to the AQL queue if device-side AQL queues
are requested and the GPU owner of the AQL doesn't support large
BAR. Otherwise, ROCr will currently allow device-side queues
that can cause faults when the user tries to touch their ring
buffers and the user will not know why the faults are occuring.
This relies on the fact that the KFD does not exposed any links
from the CPU to the GPU if large BAR is not enabled (though
links from the GPU to the CPU may still be exposed by the KFD).
Adds a bool to the GPU agent and a public member method to
check if the GPU supports large BAR. This is needed so we can
check if large BAR is supported when a user tries to allocate
an AQL queue in device memory on a given GPU agent.
Also adds an exception to the AQL queue if device-side AQL queues
are requested and the GPU owner of the AQL doesn't support large
BAR. Otherwise, ROCr will currently allow device-side queues
that can cause faults when the user tries to touch their ring
buffers and the user will not know why the faults are occuring.
This relies on the fact that the KFD does not exposed any links
from the CPU to the GPU if large BAR is not enabled (though
links from the GPU to the CPU may still be exposed by the KFD).
[ROCm/ROCR-Runtime commit: f2c482d923]
This builds on a prior change that allowed for allocating
a user-mode queue's packet buffer in device memory to also
allocate the queue struct in device memory. This provides
additional latency benefits particularly for cases where
dispatches are performed from the GPU itself. Flags are
added to support the various use cases.
This builds on a prior change that allowed for allocating
a user-mode queue's packet buffer in device memory to also
allocate the queue struct in device memory. This provides
additional latency benefits particularly for cases where
dispatches are performed from the GPU itself. Flags are
added to support the various use cases.
[ROCm/ROCR-Runtime commit: 6e3c375bf1]
* 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
Hila, Nino
Tony Gutierrez
Sang, Tao
Xie, Jiabao(Jimbo)
Choudhary, Rahul
xuchen-amd
Poag, Charis
Saleel Kudchadker
cfallows-amd
Trowbridge, Ian
GunaShekar, Ajay
Andryeyev, German
Bhardwaj, Gopesh