SWDEV-145570 - [HIP] - hipHccModuleLaunchKernel needs to be a c++ sym
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_hcc.map.in#9 edit
... //depot/stg/opencl/drivers/opencl/api/hip/hip_module.cpp#14 edit
SWDEV-145570 - [HIP] Refactored some g_* stuff
Refactored g_functions into a platform state.
Added a _vars for registered variables.
Added an execution stack similar to Hcc-clang.
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_platform.cpp#14 edit
SWDEV-2 - Change OpenCL version number from 2707 to 2708.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2455 edit
SWDEV-155434 - Add SQTT instrumentation tokens for OpenCL dispatches for RGP support
- Switch to the workgroup size report for the dispatch info.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#118 edit
SWDEV-2 - Change OpenCL version number from 2706 to 2707.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2454 edit
SWDEV-145570 - [HIP] refactor hipMemcpy* functions to correctly handle copies using prepinned memory
The current implementation of hipMemcpy functions picks the copy type based on a flag that the user passes. However, one can use the hipMemcpyHostToDevice/hipMemcpyDeviceToHost flag in a combination with prepinned memory. By using the WriteMemoryCommand/ReadMemoyCommand in this case, we will pin the same host memory twice. This is fine on PAL/Linux, since pinning the same VA range is a noop, but this will start failing once we switch to using device memory with HIP/VDI/HSA.
The solution is to ignore the hipMemcpyKind flag and let the runtime decide what kind of copy is best to do. Except for the case when hipMemcpyHostToHost is passed, since both host pointers may be prepinned.
ReviewBoardURL = http://ocltc.amd.com/reviews/r/15482/diff/
Affected files ...
... //depot/stg/opencl/drivers/opencl/api/hip/hip_memory.cpp#37 edit
SWDEV-2 - Change OpenCL version number from 2705 to 2706.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2453 edit
When shareWithAll memory (e.g., host memory) is allocated, set appId
in hc::AmPointerInfo to -1 to indicate that this memory is not mapped
to any device. Peer checking in ihipStream_t::canSeeMemory is not
necessary if memory is shared with all devices. Thus, it is skipped.
Note that earlier host memory is always mapped to device 0 and HIP
always performs peer checking for all kinds of hipMemcpy. Since the
peer checking process requires context locking, hipMemcpy from/to host
memory always grabs device 0's context lock. Therefore, if there is
another thread holding the context lock of device 0 (e.g.,
hipDeviceSynchronize on device 0), hipMemcpy will have to wait for the
lock until it can actually perform memcpy. This can significantly
deteriorate execution performance.
Signed-off-by: Sarunya Pumma <sarunya.pumma@amd.com>
SWDEV-2 - Change OpenCL version number from 2704 to 2705.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2452 edit
SWDEV-2 - Change OpenCL version number from 2703 to 2704.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2451 edit
SWDEV-132899 - [OCL][GFX10] removing gfx1001 (target for Navi10 Lite if xnack is enabled)
starting from gfx10, we will use the same target (e.g., gfx1000) no matter if xnack is enabled/disbaled and we pass "-xnack" option to Finalizer if xnack is enabled on the target
ReviewURLBoard = http://ocltc.amd.com/reviews/r/15492/
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldefs.hpp#37 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/paldevice.cpp#99 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palprogram.cpp#64 edit
SWDEV-2 - Change OpenCL version number from 2702 to 2703.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2450 edit
Maneesh Gupta
foreman
Rahul Garg
Yaxun Sam Liu
Aaron Enye Shi
Evgeny Mankov
Evgeny Mankov
lthakur
Sarunya Pumma
Brian Sumner