Pass active queue for transfers in the cache coherency layer.
That will allow to use device transfer queue only for
cases when active queue isn't available, because using device
transfer queue from another active queue may cause a deadlock
Change-Id: Ifbe7e0303b77dbf6eeda3939ffbc25a3df7472de
[ROCm/clr commit: 95d55fdfa8]
The optimization is controlled with ROCR_SKIP_KERNEL_ARG_COPY.
This is initial check-in for experiments. Extra changes are
necessary for full support:
- handle graph capture with the original sysmem alloc
- avoid memobject references, otherwise there is a race condition with
reusage of the arg buffer
- Remove arg setup from hip
Change-Id: Ib0af710f93e79834711fa4049a7c66093711e68b
[ROCm/clr commit: 7e12cf6318]
Debug builds fails with error due to missing
parentheses with -Werror=parentheses enabled
Change-Id: I5745a63b5cf2c7a3aeed90ea572081a6fa67e366
[ROCm/clr commit: 5e116c6c99]
Implementation to use a blit kernel to perform
a hipStreamWait/write instead of an AQL packet.
Change-Id: I462671ed5cec37144dfe97ff66439249196117c1
[ROCm/clr commit: cbb8d82bdb]
Cache coherency layer is OCL feature to support multiple devices in
single OCL context.
Change-Id: Ic66df9551fad5b0c4df95ab3e1db1da259919f25
[ROCm/clr commit: 6da9d18140]
std::mem_fun() and std::bind2nd() are removed in c++17. Switch to
simpler logic that does not require those functions.
Change-Id: I19a31f076e1813e367615bd377b424046ce144c7
[ROCm/clr commit: d934612948]
std: :mem_fun() is removed in c++17. Simplify logic to not require it.
Change-Id: Ic9a4753b48dd13fcb20cd5b90ff73c3df3211b9f
[ROCm/clr commit: c68f024b35]
Pass the device agent specified by the user to the ROCr api instead of passing the device agent attached to the specified stream
Change-Id: I86c98935b9dc404eaa6d47ccdd082a8c3678fb36
[ROCm/clr commit: 169cc857fd]
- Device Reset should not purge the allocations that were not by the user
- Addresses QMCPack Test abort due to the removal of all the mem objects during reset
Change-Id: I7b7a123e72bcc985d7e51d17c2382bc618d3e041
[ROCm/clr commit: 924695fb5e]
Below logic is causing a crash in the CL-GL interop. As a workaround,
limit it only to HIP.
Change-Id: I12e81d035ebd80a4a9a09eb6eea2fae7040d90c9
[ROCm/clr commit: 74ccf71d53]
Add ref counting to ProfilingSignal class to track the last release.
If a signal was used in the marker, then don't reuse it,
but create a new one for internal usage.
Don't rely on HSA callback for the command status update if there
are no pending dispatches.
Change-Id: I19f14ed9d80acfe79993b343b2187635f8428a20
[ROCm/clr commit: ff15c0893e]
HSA signal calback may occur during the actual marker submit. That
may cause a deadlock, because shared lock_ object. Create the new
notify_lock_ field to protect the notification.
Change-Id: I9752af84e59895530620fac3932c6fc276de8658
[ROCm/clr commit: f34c1b9ff8]
Runtime can't assign internal HSA signals for HIP events, because
HIP application can destroy the HIP stream or signal reuse may
occur internally. Switch to global HSA signals for HIP events.
Change-Id: Ieaea2d6b039e492b2e7c5112782a8f4e601e50a1
[ROCm/clr commit: ce8dad2ecc]
We do not want to release resources during setStatus in HIP because of Graphs
Change-Id: Idc7b188ab5f8be6975ea91005dd2bbf177401f8c
[ROCm/clr commit: 133287f31f]
If AMD event contains a reference to a HW event, then runtime
could check/wait for HW event. CPU status update will occur later
after HSA signal callback, but it's not important for the result.
Change-Id: I591391a953bbdba6a25ac07e2cd98aeb17cd4596
[ROCm/clr commit: 85c70a7495]
For DD, send a NOP packet so that we leverage the handler to indicate
completion.
Change-Id: Ie57ea0124a8497d39cc49da1c4575c2cd86b9319
[ROCm/clr commit: 9d0846e732]
German Andryeyev
Satyanvesh Dittakavi
haoyuan2
Sarbojit Sarkar
anusha GodavarthySurya
Jason Tang
Alex Xie
pghafari
Sourabh Betigeri
jujiang
agunashe
Vladislav Sytchenko
kjayapra-amd
Saleel Kudchadker
Christophe Paquot