Adobe AE allocates/destroys system memory per each frame
in some effects, which is a very expensive operation.
Disable pinning and force sysmem allocation in VidMM.
That allows to trigger resource cache in runtime and
avoid paging operations, caused by pinning.
The actual benchmark doesn't have significant improvement
from the change, but GPU view traces are much cleaner.
Change-Id: I92cdd87d37c64611788f05250f71d6fe489b4d7e
Pinned copy can cause big performance drops, because slow pinning under Windows.
Use up to 128MB for staging transfers. Change staging buffer size to 4MB.
Linux path should still have the old defaults.
Change-Id: I954edceb3ec89e8e670be116aa2d0a9564c8b11c
Sync between compute and SDMA engines can be very expensive under Windows.
Use CP DMA for tiny transfers (< 1KiB) to avoid syncs and improve performance.
Change-Id: I9db39a2199f7b9e337ed08fd36d9cbc150502f1f
HIP can't rely on the resource tracking, used in OCL and requires different explicit sync.
Make sure ROCCLR syncs compute only when SDMA is used and vise versa.
The new logic will allow to enable CPDMA without unnecessary waits.
Change-Id: Ib9d1788cfd5afa5ea2fec4c96a37d8b9c4d0059d
Blender creates and destroys big allocations during the benchmark.
That causes big delays, because vidmm has to page-in/page-out memory.
Change-Id: I2baf4545807127406e3d2870a7581ff9ae7bcdb5
- 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
- Use a dirty flag to determine fence optimization
- If fence is dirty submit a marker at top level to sync.
Change-Id: I53fb19b5bb05b7c7b37c41637a6c7aaf870b639a
assert statement were hit silently in Release builds like SWDEV-353548.
Issue only seen in Debug builds
Change-Id: I9f7177806c854d64fcf986e9f6092076d8a05f23
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
Introducing a VirtualMemObj map as it is needed to differentiate
between virtual address ranges and actual physical memory
This is because a whole VA range can have several physical memories
as chunks.
Change-Id: Ie2a972b4faf3f7d552cfa53e77898f80ad75740a
The heap must be cleared once per device, but ROCclr doesn't
create a queue per device in HIP. Hence, the clear operation will
be performed during the first queue creation.
Change-Id: I52ceb06d67d11cde6d019c5ab510059f426a9bfb
This code change is to improve error handling.
This code change does not fix issue itself.
Before this code change, hostcallBuffer_ point is initialized in the end of
create() function. If create function fails and returns early,
hostcallBuffer_ point is not initialized. This non-initialized point can
cause access violation when object is destructed.
This code change put the initialization of the pointer in the constructor.
Change-Id: I7fb6e764eb0547196dca03db237e49d3ff0fd06a
jatang
Todd tiantuo Li
Ioannis Assiouras
Jaydeep Patel
German
Tao Sang
Julia Jiang
kjayapra-amd
Alex (Bin) Xie
Sourabh Betigeri
Ajay
Christophe Paquot
Saleel Kudchadker
Rakesh Roy
jie1zhan
Sarbojit Sarkar
sdashmiz
Alex Xie