The cl_khr_depth_images associated macro definition is defined twice in
the compiler: in opencl-c.h and automatically by the compiler deduced
from the cl-ext list. These two co-exist and there is no need to remove
cl_khr_depth_images from the cl-ext list.
If we remove cl_khr_depth_images from the cl-ext list, and we do not
include opencl-c.h the macro is not defined.
This fixes conformance test ./test_compiler compiler_defines_for_extensions
when using Comgr with -include opencl-c-base.h -fdeclare-opencl-builtins
without including opencl-c.h.
Before we got the error `ERROR: Supported extension cl_khr_depth_images
not defined in kernel`
This change is needed to eventually get rid of the opencl-c.pch that is embedded in comgr, and that makes implementing a compilation cache in comgr hard.
Change-Id: I76497874ebe7163966420d4ac23a0788b93a36fd
- Resolve signal dependencies for barrier value packet if there are > 1
depenent signals. Barrier Value packet accounts for only 1 dep signal
- Better log
Change-Id: Ia506ad5d80b91d598f92e7b539f41756e9b4b64b
This change fixes random segfaults in graph tests that
are seen after the change make internal callbacks non-blocking.
The callback thread that decreases the GraphExec ref count
may now run after the runtime shutdown. This can cause a segfault
because the hip::device that is accessed in GraphExec destructor
is already destroyed during runtime shutdown. This patch ensures
that the hip::device object stays alive until after the
callback thread completes.
Change-Id: I75a6ac01f27a0b2250bbd10ed389ebfb322927af
Adds UberTrace support for pre-dispatch markers and barrier begin/end markers.
Moves shared definitions out of palgpuopen.hpp into shared header
palcapturemgr.hpp.
Change-Id: I9f464c689e7ff12c54eca043fc1ad65e1836a64f
- When using shader copy, make sure to use release scope for the AQL
packet. This is a potential bug but is hidden as hipMemcpyAsync always
needs synchronization(which inserts a barrier with release scope). For
hipMemcpy we use a barrier packet to make sure its blocking. Eitherways
a barrier gets always used and hides in some ways a potential bug.
Change-Id: I57fb7f769c3179e76d712471c0905104c801d7ba
- When we use blit(compute) copies, two subsequent copies may read for
the same source buffer, the buffer may get modified by the host in
between and if the src buffer was allocated with non-coherent flag, the
device may simply use stale value from previous cacheline fetch. This is
a corner case.
Change-Id: I2ce261c6f6fa4e5bb608f116548e5cc711ae6f3c
We are passing this arg as an address, and memcpy complains about
overreading (8 bytes instead of 4).
Change-Id: Ica9207f6c5f6056a4bfc968280c76e779ded13ae
- Added DEBUG_CLR_SKIP_RELEASE_SCOPE flag to force release scope to
SCOPE_NONE in AQL packet header
Change-Id: Ife02cddb9d5cd4749103ce585d3d5fe9024c6868
Uri decoder logic currently silently ignores processing of memory uri.
This patch enables the existing logic to handle the processing of offset
and size related to loaded code-object having memory URI.
Change-Id: If03579cefb11d91f667410464dc89404df9270a3
Support gfx9-4-generic target to cover mi3XX.
Support features sramecc and xnack in generic target.
Improve some code formats.
Add more log on compiler.
Change-Id: I6b3c6af55c60cffd43ce6f17b75998f751b75713
In active wait mode use signals without interrupts by default and switch
to the interrupts only if a callback is required.
Change-Id: Ibcde8f7d44c70f8fb8fa5e0a7fdd8b08a2982a8e
- Refactor blit code and clean ASAN instrumentation
- Use unified function for rocr copy
- Enable shader copy path for unpinned writeBuffer/readBuffer paths
- Set GPU_FORCE_BLIT_COPY_SIZE=16 which means we will use BLIT copy for
pinned copies or unpinned H2D/D2H copies < 16KB
Change-Id: I42045cca79234b340dbf53dafb93044199736ae4
The early return if the thread is not alive causes memory leaks.
Neither doorbell_ or urilocator are released if the thread is not alive.
This change alters the logic so regardless of the thread status the
HostcallListener releases its memory.
Change-Id: Ie912360ec0e2ee257de9937b1a8d7375e6aebd83
hsa_amd_profiling_async_copy_enable is taking 45us for the first call. Disable sdma profiling for enqueuing captured kernel packets and for accumulate command.
Change-Id: I80b51a58c46bccc9c1025e9331515f57c97b5a2a
Runtime may use checkGpuTime() for the wait and not just for the GPU time queries. Hence, the call can't be skipped if profiling isn't enabled.
More changes are required for this optimization.
Change-Id: I79e8918312e755d75f0d26685f2fdc604a8ffb18
Juan Manuel Martinez Caamaño
Jimbo Xie
taosang2
kjayapra-amd
Saleel Kudchadker
German Andryeyev
Ioannis Assiouras
Jatin Chaudhary
Aidan Belton-Schure
Daniel Livingston
Anusha GodavarthySurya
Evgenii Averin
Sourabh Betigeri
Pengda Xie
Amit Pandey
Gerardo Hernandez
Ajay
Jaydeep Patel