Note hipHostMalloc (not hipHostAlloc or hipMallocHost).
- the hipHost* is used for all HIP APIs dealing with Host memory.
(including hipHostMalloc, hipHostFree, hipHostRegister,
hipHostUnregister, hipHostGetFlags, hipHostGetDevicePointer).
- hipMallocHost is consistent with "hipMalloc" for allocating device
memory. Enumerations hipHostMalloc* also used as optional
flags parm to hipHostMalloc.
[ROCm/clr commit: 2d0fade1f7]
SWDEV-2 - Change OpenCL version number from 2070 to 2071.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1817 edit
[ROCm/clr commit: 081797160c]
SWDEV-90408 - OpenCL runtime crashes when querying CL_PROGRAM_NUM_KERNELS on a program built with clCompileProgram
- The app attempts to get query before build/link call. Make sure symbols are available.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#39 edit
[ROCm/clr commit: c2b98ee500]
SWDEV-90408 - OpenCL runtime crashes when querying CL_PROGRAM_NUM_KERNELS on a program built with clCompileProgram
- The app attempts to get query before build/link call. Make sure symbols are available.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_program.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/program.hpp#39 edit
[ROCm/clr commit: 769ff6d3f8]
SWDEV-2 - Change OpenCL version number from 2069 to 2070.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1816 edit
[ROCm/clr commit: 19564646c7]
SWDEV-2 - Change OpenCL version number from 2068 to 2069.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1815 edit
[ROCm/clr commit: d58bf7ea73]
These will print compiler warnings if used, so we can weed them out
before removing.
Also add a default flags args for hipHostAlloc, in the C++ functioin
headers. So you can replace hipMallocHost(&ptr, size( with hipHostAlloc(&ptr, size)
[ROCm/clr commit: 57365eb7a3]
- move waitAllStreams to device member function.
- create separate stream member function for copyAsync, like copySync.
hipMemcpyAsync now calls the copyAsync.
[ROCm/clr commit: a88c2b1ec9]
- NULL stream was waiting for itself to be empty before each command.
- Force "blocking" streams to wait for NULL to empty. This was missing
before.
- async copy was disabling itself via trueAsync=false for common cases.
Refactor:
- rename _null_stream to _default_stream.
- move some null sync function to defaultSync, move to dev member func.
[ROCm/clr commit: 44522eb607]
SWDEV-2 - Change OpenCL version number from 2067 to 2068.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1814 edit
[ROCm/clr commit: ef7612cfb3]
-Move staging buffer locks inside the staging buffer code.
-Remove dedicated per-device completion_signal + per-device lock -
instead allocated signal from the per-stream pool. This elimintes
the lock and allows more concurrency.
-remove switch HIP_DISABLE_BIDIR_MEMCPY
[ROCm/clr commit: e64174f47a]
SWDEV-2 - Change OpenCL version number from 2066 to 2067.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1813 edit
[ROCm/clr commit: 35181ad34b]
- refactor staging buffer to operate on hsa* data structures not
hc::accelerator.
- use hsa_memory_allocate to allocate staging buffers rather than
am_alloc.
- Refactor device reset with single member function. Don't reallocate
staging buffers on reset.
- Properly track dependencies based on command type. Add new deps for
H2D and D2D rather than overloading H2D.
[ROCm/clr commit: 3b45e064f9]
SWDEV-2 - Change OpenCL version number from 2065 to 2066.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1812 edit
[ROCm/clr commit: 5a093ba1e9]
Still #include staging_buffer.cpp into hip_hcc.cpp.
Directed tests compile hip_hcc to static library and use the library.
[ROCm/clr commit: a1879ba59b]
dfukalov
foreman
Ben Sander
Aditya Atluri
Aditya Atluri