- Use a dirty flag to determine fence optimization
- If fence is dirty submit a marker at top level to sync.
Change-Id: I53fb19b5bb05b7c7b37c41637a6c7aaf870b639a
- Store last fence scopes and use the last value to determine if we need a cache flush again. This helps cases where hipExtLaunchKernel API is
used.
- Purge code for ROC_EVENT_NO_FLUSH
Change-Id: I531cf9c9c60d5e2b3a9e265d0f52f79ed2fa8a8c
Remove the activity_prof::CallbacksTable. The table was redundant with
the information already stored in the roctracer library. Instead use a
single callback into the roctracer library to query whether the activity
is enabled, and to report it.
Change-Id: I2e05b0881bb4a1953c14361d00ea310d02eb6e0c
If the execution command had a split into multiple HW operations, then runtime has to accumulate time for all operations
Change-Id: Iaba31e96250918d8190bf63adb4c07730fdfefbf
Maintain status of handler callback. For event records we no longer
submit callbacks to reduce the load on the async handler thread. However
without a callback we leak command memory/decrement refcounts. Indicate
status of the handler which we can use to queue a callback when
finish is called.
Change-Id: I89fd02f3d047a0e8162664ee17581a14795f1928
Move hidden heap creation to the kernel launch to make sure it's
allocated on the actual first usage.
Change-Id: I1b65a82fc06d9129ed45a69765bf14ea3d945b04
Disable hostcall buffer in OCL for now. COv5 can add hostcallbuffer
metadata for unknown reason. OCL may fail the buffer allocation
and kernel launch.
Change-Id: I34a6a45bac86c57422b764c0d69760c96920d6c5
- check pcie atomci support for printf functionality
- if not enabled printf wont work
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ib366e8e71772b02210c4a830bca4bd8cc7a11664
- Add a global cache state for a device to indicate scopes of submitted
AQL packets
- Remove scopes for TS marker if hipEventReleaseToDevice is passed. Set
env ROC_EVENT_NO_FLUSH=1 to use NOP AQL for event records.
It would flush caches by default with system scope release.
- Calling finish() should ensure if caches are flushed, if not queue a
marker
Change-Id: Ibbbdbb1cd7ac61cb35649169212142545be159e0
Remove assert for kernel arg size, because COv5 reports a value
bigger than the actual usage in the most of cases
Change-Id: I8e15bc45a9e21b58a5894f9977511ca84408ce61
- Fix a crash with AMD_CPU_AFFINITY=1 as numa_bitmask_alloc isnt the
right api to allocate bitmask
- Do not set affinity for ROCr thread. It worsens performance rather
than any improvement.
- Fix regression from my previous change for event handler.
Change-Id: I3ea75adc2a6333f29752283eddd5b555e9b58cc5
- Queue handler for hipEventRecord(aka marker_ts_) only if there is a
callback associated with it.
Change-Id: I8a9877ae0e342556053abbaacc9510744a8e772a
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
If GlobalMemCacheLine reported is 0, runtime may run into an
infinite loop as the KernelSegmentAlignment is chosen as size of the
cache line.
Change-Id: Ide547940cc0407f16fab10ee210b4fd3ae4eaafc
Metadata in Codeobject version 5 is the extension of CO3 and CO4.
Add the detection of the new fields and program them in
the setup of the kernel arguments.
Change-Id: I27e58df77320ad00f4f16d35912668db803826af
Add a state indicator to retain ExternalSignals when needed.
Co-operative group launch uses external signals to indicate a dependency
to the next command.
Change-Id: I6d0daa006e2377c3bbf4aeca0fd5b63c7ac8fbbb
Crash was due to the fact that external signal structure was stale even
after destroyign the command. That is because we skipped wait due to a
missing check.
Detect external signals and dispatch a barrier in ReleaseGpuMemoryFence.
Also clear external_signals_ at ProfilingBegin.
Change-Id: I991387edcfe928b511bf5e780988ee131321ed5a
Add a threshold for ROCR/SDMA P2P transfers. ROCR copy path
requires extra barriers in compute for synchronization. That costs
extra performance with tiny transfers.
Reduce active wait time to 10us. Tensorflow uses extra thread
per GPU with constant hipEventQuery() calls. Longer active waits
in ROCr affect CPU performance.
Change-Id: I9020358438615fa2d4617f862f00a562f0a588e7
Stall in the host thread could occur earlier than the app expects.
Make sure rutnime can grow the signals to the queue size without
any stall. Also adding a new signal to the end of the pool could
break the dependency chain on signal reuse. The new logic will
insert the new signal after current to keep the chain intact.
Change-Id: I9c90b98515907db8b677528263c3e88cd9581a14
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
The kernel arg pool will be divided into 8 chunks to avoid long stalls,
when the pool will be reused.
Change-Id: I228e6ca1c09e428c1775f1e5b685220a9a5d71af
Saleel Kudchadker
Sourabh Betigeri
Laurent Morichetti
Rakesh Roy
German
Maneesh Gupta
Sarbojit Sarkar
kjayapra-amd
Ajay
Jason Tang
sdashmiz
Julia Jiang
Maxime Chambonnet
Satyanvesh Dittakavi