+ Both Driver API and RT API are supported and synced with each other
+ Update *.md docs and hipify-perl accordingly
+ Add new conversion type "virtual_memory", introduced in Dirver API
[ROCm/clr commit: 43441eb99c]
SWDEV-2 - Change OpenCL version number from 3052 to 3053.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2800 edit
[ROCm/clr commit: 7d544e807f]
[Background] it was found that if lazy linking used for a library that calls hipExtLaunchMultiKernelMultiDevice API then this API can get the wrong program_state object for looking up device kernels leading to a "No device code available" error in this API.
To fix this issue, the API was refactored to be inline and get and pass the correct program_state to an internal hip API to request a multi-device kernel launch.
[ROCm/clr commit: 8eaea4d114]
SWDEV-2 - Change OpenCL version number from 3051 to 3052.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2799 edit
[ROCm/clr commit: 0814a17a4e]
SWDEV-2 - Change OpenCL version number from 3050 to 3051.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2798 edit
[ROCm/clr commit: 2c697a17e2]
+ Update *.md docs and hipify-perl accordingly
[Reason]
Starting with CUDA 10.1 all error codes are merged between Driver and RT APIs
[ToDo]
Do the same merge in HIP API as there is no need in distinguishing return codes by API
[ROCm/clr commit: 636108aaa9]
SWDEV-214490 - Update HIP RT for texture3D in HIP/PAL on Windows
- Update function hipMemcpy3D for Texture Array
- Add hipArrayCubemap support in hipMalloc3DArray
http://ocltc.amd.com/reviews/r/18328/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#88 edit
[ROCm/clr commit: 384f95a8be]
SWDEV-2 - Change OpenCL version number from 3049 to 3050.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2797 edit
[ROCm/clr commit: b39b9582d9]
SWDEV-2 - Change OpenCL version number from 3048 to 3049.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2796 edit
[ROCm/clr commit: fc6a848e84]
SWDEV-2 - Change OpenCL version number from 3047 to 3048.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2795 edit
[ROCm/clr commit: 1d9815dd75]
SWDEV-204782 - introduce hostcall
Hostcall is a service that allows a kernel to submit requests to the
host using shared buffers, and block until a response is received. This
will eventually replace the shared buffer currently used for printf, and
repurposes the same hidden kernel argument.
When the runtime launches a kernel that requires the hostcall service it
performs the following actions:
- Launch a hostcall listener thread if it is not already running.
- Locate the hostcall buffer for the corresponding hardware queue, or
create a new one.
- Register the new hostcall buffer with the listener thread.
- Set the hostcall buffer pointer as an implicit argument to the kernel.
Affected files ...
... //depot/stg/opencl/drivers/opencl/make/hip.git/tests/Makefile#21 edit
... //depot/stg/opencl/drivers/opencl/make/hip.git/tests/build/Makefile.hip_tests#31 edit
... //depot/stg/opencl/drivers/opencl/make/hip.git/tests/scripts/hip_hostcall_tests.txt#1 add
... //depot/stg/opencl/drivers/opencl/make/hip.git/tests/scripts/run_all_tests.sh#22 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.cpp#30 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/devkernel.hpp#19 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.cpp#143 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocdevice.hpp#45 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rochostcall.cpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rochostcall.hpp#1 add
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#92 edit
[ROCm/clr commit: 416f273e94]
SWDEV-2 - Change OpenCL version number from 3046 to 3047.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2794 edit
[ROCm/clr commit: 9d20a77b81]
SWDEV-2 - Change OpenCL version number from 3045 to 3046.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2793 edit
[ROCm/clr commit: e2cdf665e4]
SWDEV-213526 - pytorch tests fail with hipErrorOutofMemory
There's a bug in ROCr when loading a lot of kernels and not syncing
So for now, if an allocation fails, sync devices and retry before
returning hipErrorOutOfMemory error.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#86 edit
[ROCm/clr commit: e7745c6d1e]
SWDEV-79445 - OCL generic changes and code clean-up
- Don't sync on the scratch buffer if the executed kernel is unchanged, since the number of scratch regs remains the same
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#158 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#65 edit
[ROCm/clr commit: dd5459c7a1]
SWDEV-2 - Change OpenCL version number from 3044 to 3045.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2792 edit
[ROCm/clr commit: cabcfb5f37]
SWDEV-212749:
o Recent changes to “add support for extended launch” require hip_runtime.h to be include in hip_ext.h
o Order in which external applications include hip_hcc.h/hip_runtime.h causes compilation failure
[ROCm/clr commit: e5fc5aa41c]
SWDEV-2 - Change OpenCL version number from 3043 to 3044.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2791 edit
[ROCm/clr commit: e4d5473068]
Handled the HCC version check appropriately as few of the directed tests (SWDEV-212161) were failing when hcc was bumped to 3.0.
[ROCm/clr commit: d4dde7a27d]