- Make sure SQQT trace is captured for RGP server if the queue is destroyed before normal capture is done.
- Remove prepare queue from the logic. It's not really used for any HW capture and can cause RGP server abort if destroyed before capture is even started(delayed capture)
Change-Id: I6eb19963190a5769c6477a5496c1b831a6d59b89
In X86 on Windows, sizeof(size_t)=4, but size=8, for
amd::KernelParameterDescriptor::HiddenGlobalOffsetX/Y/Z items.
Loose the condition to prevent crash.
Change-Id: I2216f71f4d4fd6dd3766023b1c821cb3d35d7848
The ROCclr assigns zero-based IDs to GPUs in the order they are
discovered. That zero-based ID is what is used to identify the GPU
on which the HIP_OPS activity took place.
When multiple ranks are used, each rank's first logical device always
has GPU ID 0, regardless of which physical device is selected with
CUDA_VISIBLE_DEVICES. Because of this, when merging trace files from
multiple ranks, GPU IDs from different processes may overlap.
The long term solution is to use the KFD's gpu_id which is stable
across APIs and processes. Unfortunately the gpu_id is not yet exposed
by the ROCr, so for now use the driver's node id.
Change-Id: Ib78854527d600d175bb76e2df0747c33f898c615
- 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
assert statement were hit silently in Release builds like SWDEV-353548.
Issue only seen in Debug builds
Change-Id: I9f7177806c854d64fcf986e9f6092076d8a05f23
If the execution command had a split into multiple HW operations, then runtime has to accumulate time for all operations
Change-Id: Iaba31e96250918d8190bf63adb4c07730fdfefbf
- rocr attribute needs to be updated after each iteration
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I3afb2d7954ef3de37f5f5f9d3cc7757fdacffcec
- Leverage managed buffer that would use chunks for fill pattern. Use a
different chunk for the next fill to avoid wait
Change-Id: I254483c867e112f66564ffd8f55e0a605d8896c9
- Make sure head_size is not crossing fill_size
- Head size, aligned size & tail size together cannot cross fill size
Change-Id: Ie7845d748e3698b245876b43c9e626d7ea7154f7
- In ROCr, there is supposed to be exactly one HSA signal ever whose pointer is stored in every hostcall buffer so that device code can find it
- But, hostcallListener->initDevice creates a new HSA signal everytime enableHostcalls() gets called
Change-Id: I100595ec37442bcdb73da5991062f0a474de2935
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
Ajay
German
Alex (Bin) Xie
Tao Sang
Sourabh Betigeri
Laurent Morichetti
Julia Jiang
Christophe Paquot
kjayapra-amd
Saleel Kudchadker
Maneesh Gupta
Rakesh Roy
Yifan Zhang
Sarbojit Sarkar
jie1zhan
Satyanvesh Dittakavi
sdashmiz
Alex Xie
Anusha Godavarthy Surya
Jaydeep Patel
haoyuan2