Prevents OOM-Killer trigger,if all physical and swap mem gets fully used
Change-Id: I70d558fa9c06fe6217e62d57e11aec6a089aa0bb
[ROCm/ROCR-Runtime commit: 13800cc6d5]
Adjust code to allow the use of non-contiguous chunks of memory to be
mapped within a single VA range.
Change-Id: Ida21ba202927229347b3a32d9b7106df10819cf5
Adjust code to allow the use of non-contiguous chunks of memory to be
mapped within a single VA range.
Change-Id: Ida21ba202927229347b3a32d9b7106df10819cf5
[ROCm/ROCR-Runtime commit: f7de85082e]
Add tests to catch whether ROCr breaks ABI compatibility with the
hsa_amd_pointer_info API in case the hsa_amd_pointer_info struct is
extended.
Change-Id: I4e69bf30db9791e59f895b2798b87985c41242e5
Add tests to catch whether ROCr breaks ABI compatibility with the
hsa_amd_pointer_info API in case the hsa_amd_pointer_info struct is
extended.
Change-Id: I4e69bf30db9791e59f895b2798b87985c41242e5
[ROCm/ROCR-Runtime commit: 776da1a3f7]
Add new tools table and functions to notify in case of an event
Change-Id: I47f0c2f3c8e02d7bcb74d649903eb4f86721c154
[ROCm/ROCR-Runtime commit: a67af3807f]
Currently, the definition of hsa_amd_memory_fault_reason_t tries to
set a constant of 0x8000_0000 by using the definition "1 << 31".
However, the 1 in this definition is a signed integer by C++ rules.
On our architectures, shifting a signed integer by 31 results in
signed integer overflow. Signed integer overflow results in
undefined behavior.
Forcing the 1 to be unsigned avoids this.
Change-Id: I860431eeede4eff29598f646abf3c1337b048d71
Currently, the definition of hsa_amd_memory_fault_reason_t tries to
set a constant of 0x8000_0000 by using the definition "1 << 31".
However, the 1 in this definition is a signed integer by C++ rules.
On our architectures, shifting a signed integer by 31 results in
signed integer overflow. Signed integer overflow results in
undefined behavior.
Forcing the 1 to be unsigned avoids this.
Change-Id: I860431eeede4eff29598f646abf3c1337b048d71
[ROCm/ROCR-Runtime commit: 1d6691e06b]
Fix gang factor overwrite of 0 if there are no xGMI SDMAs
on the device and gang factor is 1.
Change-Id: I041d4b4ae87fb68f224ee4dedb758c6f06c022a9
[ROCm/ROCR-Runtime commit: 1dd4a7dc18]
The @platform alias will describe which platform (for example,
gpu_baremetal or/and host) an API can be used.
The get_platform.py is a tool to compare APIs in different platforms.
Change-Id: I902bc4fea048269eace6e9f3f4a8e93f3adb7f87
The @platform alias will describe which platform (for example,
gpu_baremetal or/and host) an API can be used.
The get_platform.py is a tool to compare APIs in different platforms.
Change-Id: I902bc4fea048269eace6e9f3f4a8e93f3adb7f87
[ROCm/amdsmi commit: 86d025daaa]
Added global flag g_IsEmuMode and set it when running under emulator.
Adjusted delays in KFDCWSRTest for emulator.
Change-Id: Ia5c0be40816ac2219add943e306ee16438f5b852
Signed-off-by: David Belanger <david.belanger@amd.com>
Added global flag g_IsEmuMode and set it when running under emulator.
Adjusted delays in KFDCWSRTest for emulator.
Change-Id: Ia5c0be40816ac2219add943e306ee16438f5b852
Signed-off-by: David Belanger <david.belanger@amd.com>
[ROCm/ROCR-Runtime commit: 3dd98d075f]
- Updated header and source files
- Updated python interface
- Generated python wrapper for updated header
- Updated the CLI to have cpu family & cpu model
as part of metric table
Change-Id: Iea440251797270d5d29ffe883b0ad6db790be658
- Updated header and source files
- Updated python interface
- Generated python wrapper for updated header
- Updated the CLI to have cpu family & cpu model
as part of metric table
Change-Id: Iea440251797270d5d29ffe883b0ad6db790be658
[ROCm/amdsmi commit: 6f7273fda5]
Users can import device memory without specifying the target node.
DMA buf imports return a Thunk handle that's not useful for
gpu mapping calls.
Fix this by using the import node information to re-import and
map with the correct target GPU.
Also fix IPC detach calls by deregistering the Thunk handle
import immediately during attach instead of failing to do it later
on detach since Thunk handles aren't placed into ROCr allocation
map.
Finally refactor the IPC attach function for cleaner logic flow.
Change-Id: Ib2bf178110b2be98bd6917c765f724e4e613f5f2
Users can import device memory without specifying the target node.
DMA buf imports return a Thunk handle that's not useful for
gpu mapping calls.
Fix this by using the import node information to re-import and
map with the correct target GPU.
Also fix IPC detach calls by deregistering the Thunk handle
import immediately during attach instead of failing to do it later
on detach since Thunk handles aren't placed into ROCr allocation
map.
Finally refactor the IPC attach function for cleaner logic flow.
Change-Id: Ib2bf178110b2be98bd6917c765f724e4e613f5f2
[ROCm/ROCR-Runtime commit: a3efd13a2f]
We should also close the client side dmabuf fd after importing for target
nodes.
Change-Id: I74f61dd65bebb03dc002f5df7301efd1ef8d9603
[ROCm/ROCR-Runtime commit: 15691ae460]
Shweta Khatri
jujiang
David Yat Sin
Mythreya
Joseph Greathouse
Jonathan Kim
Nick Curtis
Rahul Manocha
Bill(Shuzhou) Liu
kjayapra-amd
Maisam Arif
Satyanvesh Dittakavi
Anusha GodavarthySurya
David Belanger
Galantsev, Dmitrii
Deepak Mewar
dependabot[bot]