For OCL, keep original control logic
FOr HIP, keep the fix for SWDEV-338781
Change-Id: I89de8d1e73cd103b3b4f62206eed72d45695dd6e
[ROCm/clr commit: 0a43f6bff3]
- 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
[ROCm/clr commit: 42da508815]
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
[ROCm/clr commit: 5df34a2f7a]
Move hidden heap creation to the kernel launch to make sure it's
allocated on the actual first usage.
Change-Id: I1b65a82fc06d9129ed45a69765bf14ea3d945b04
[ROCm/clr commit: 4975f69337]
Move StartLateDeviceInit() and FinishDeviceInit() calls in RGP
server to avoid a timeout
Change-Id: Ifd681859c7dc76259d7296aa8cc15305d563c9b2
[ROCm/clr commit: ecea224bcf]
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
[ROCm/clr commit: 905088e4e7]
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
[ROCm/clr commit: 04bfd93569]
Set release scope as system for dispatch AQL when events are passed to
hip*LaunchKernelGGL*
Change-Id: I93b91591e0ab023f1ecc5247f7905eca26147358
[ROCm/clr commit: 02566677cf]
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
[ROCm/clr commit: 934149ff0a]
Disable devlib linking when runtime links multiple objects from
the app. Otherwise devlibs will be linked twice and may cause
undefined behavior with COv5.
Change-Id: I3b8640c64ff898893225fe3af5b4b4a32d42bf40
[ROCm/clr commit: c275d9b4b3]
Implement map/unmap for PAL backend
Create commands since PAL uses the IQueue to map/unmap
Change-Id: I97e26a7d28ae5e10774c9ca65307153100945621
[ROCm/clr commit: 67657d6099]
- check pcie atomci support for printf functionality
- if not enabled printf wont work
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: Ib366e8e71772b02210c4a830bca4bd8cc7a11664
[ROCm/clr commit: 15f1632dfa]
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
[ROCm/clr commit: 5528812aa9]
Adding virtual memory management APIs to rocclr.
The HIP layer will handle virtual allocs on devices.
Change-Id: Ia978f105c2c3fed3959c77580ba228e845105754
[ROCm/clr commit: b5f555f9ec]
- 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
[ROCm/clr commit: 8eeaa998c0]
Remove assert for kernel arg size, because COv5 reports a value
bigger than the actual usage in the most of cases
Change-Id: I8e15bc45a9e21b58a5894f9977511ca84408ce61
[ROCm/clr commit: 2be0b1e612]
With COv5 local size calculation must occur before
runtime programs kernel arguments
Change-Id: I0726c6529bde69b8fcf5360aa83986cf84e04168
[ROCm/clr commit: caa6110c29]
kjayapra-amd
German Andryeyev
Christophe Paquot
haoyuan2
Rakesh Roy
Saleel Kudchadker
Sarbojit Sarkar
Julia Jiang
Ajay
Jason Tang
sdashmiz
Alex (Bin) Xie
Alex Xie
pghafari
Maxime Chambonnet